Research on Software Reliability Model Based on Improved Bp Neural Network

Abstract

Neural network has good fault-tolerant ability, classification ability, parallel processing ability and so on, so the research of software reliability model based on neural network is paid more and more attention. Bp neural network has strong nonlinear mapping ability and flexible network structure, so BP neural network is currently used in various fields. In this paper, a software reliability model optimized by hidden layer BP neural network is proposed and the training process of BP algorithm on this model is described.